https://github.com/amilworks/3d-xception
Facebook DeepFake Detection Challenge: PyTorch 3D Xception Network for Video Classification
Science Score: 23.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (6.9%) to scientific vocabulary
Keywords
Repository
Facebook DeepFake Detection Challenge: PyTorch 3D Xception Network for Video Classification
Basic Info
Statistics
- Stars: 8
- Watchers: 2
- Forks: 0
- Open Issues: 0
- Releases: 1
Topics
Metadata Files
README.md
3DXception
Author: Amil Khan
Background
This repository consists of a PyTorch implementation of 3DXception, a convolutional neural network for video classification. The code enables users to train 3DXception for problems in video classification, but has not been tested for data outside videos such as volumetric data. This network is based on the successful Xception network by François Chollet. The paper is Xception: Deep Learning with Depthwise Separable Convolutions and I highly recommend you check it out. For convenience, I will attach an abridged version of Chollet's Xception Paper Abstract:
Abstract: We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a pointwise convolution). In this light, a depthwise separable convolution can be understood as an Inception module with a maximally large number of towers. This observation leads us to propose a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have been replaced with depthwise separable convolutions.
Prerequisites
- Linux (Tested on Ubuntu 16.04 and 18.04)
- NVIDIA GPU
- CUDA
- Docker (Recommended)
Getting Started
There are two routes you can take, but I highly suggest the Docker installation. Why? Because Docker is awesome. Okay, besides that, I have already packaged everything you need to get started with dataloading, visualizing, preprocessing, training, postprocessing, whatever you need, I probably got you.
Pull Docker Container
docker pull docker.pkg.github.com/amilworks/3d-xception/3d-xception:v0.1.0
Owner
- Name: Amil Khan
- Login: amilworks
- Kind: user
- Location: UCSB
- Company: UCSB Electrical & Computer Engineering
- Website: amilworks.github.io
- Repositories: 2
- Profile: https://github.com/amilworks
PhD student in Electrical & Computer Engineering @ucsb, Lead Engineer @ BisQue
GitHub Events
Total
Last Year
Issues and Pull Requests
Last synced: 11 months ago
All Time
- Total issues: 1
- Total pull requests: 0
- Average time to close issues: almost 2 years
- Average time to close pull requests: N/A
- Total issue authors: 1
- Total pull request authors: 0
- Average comments per issue: 0.0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- Le0v1n (1)